Pith. sign in

REVIEW 6 cited by

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.17717 v3 pith:2YBTOFVS submitted 2023-11-29 cs.CV cs.LG

Chi-Pin Huang , Kai-Po Chang , Chung-Ting Tsai , Yung-Hsuan Lai , Fu-En Yang , Yu-Chiang Frank Wang This is my paper · ORCID
classification cs.CVcs.LG
keywords conceptdiffusionerasingimageslightweightmodelsrecelerreliable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable. The former refrains the model from producing images associated with the target concept for any paraphrased or learned prompts, while the latter preserves its ability in generating images with non-target concepts. In this paper, we propose Reliable Concept Erasing via Lightweight Erasers (Receler). It learns a lightweight Eraser to perform concept erasing while satisfying the above desirable properties through the proposed concept-localized regularization and adversarial prompt learning scheme. Experiments with various concepts verify the superiority of Receler over previous methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate

    cs.CV 2025-06 conditional novelty 6.0 of 10

    CPE uses nonlinear residual attention gates with anchoring and adversarial training to erase target concepts from text-to-image diffusion models while preserving remaining concepts better than prior fine-tuning methods.

  2. ACE: Anti-Editing Concept Erasure in Text-to-Image Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    ACE trains a LoRA adapter on both conditional and unconditional noise predictions so that erased concepts are suppressed during both generation and text-guided editing.

  3. AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors

    cs.LG 2024-12 conditional novelty 6.0 of 10

    AdvAnchor generates adversarial anchors, embeddings perturbed to be dissimilar from the target concept, and fine-tunes the model toward them, improving the erasure-preservation trade-off in diffusion model unlearning.

  4. Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A bilevel training procedure that simultaneously restores a pruned diffusion model's quality and suppresses targeted concepts beats sequential fine-tuning followed by unlearning.

  5. Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A system-first taxonomy and literature synthesis of multimodal unlearning across vision, language, video, and audio, with datasets, benchmarks, metrics, applications, and open challenges.

  6. DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

    cs.CV 2025-01 conditional novelty 5.0 of 10

    DuMo erases target concepts from text-to-image models by adding a frozen-backbone skip-connection eraser with learned timestep and layer modulation, reporting the best trade-off on three concept erasure benchmarks.

Pith tools